Systems and methods for evaluating hospital care of infection patients using length-of-stay estimation models

Abstract

Systems and methods for infection treatment evaluation is provided. The system receives patient encounter records including patient attribute data and patient LoS data. The system generates, via an LoS estimation model, LoS estimations based on the patient attribute data of each of the patient encounter records. The patient attribute data includes vital sign data, patient demographic data, laboratory data, medical condition data, infection type data, medication administration data, and/or discharge type. The system further generates, via a metric analyzer, evaluation metrics based on the LoS estimations and the patient LoS data of each of the patient encounter records. The system may also include a user interface configured to display at least a portion of the one or more evaluation metrics. The system may also train the LoS estimation model with a historical encounter records. Each of the historical encounter records includes historical attribute data and historical recovery data.

What is claimed is: 
     
         1 . A system for infection treatment evaluation comprising a controller having a processor and a memory, wherein the controller is configured to:
 receive one or more patient encounter records, wherein each of the one or more patient encounter records comprises patient attribute data and patient length of stay (LoS) data;   generate, via an LoS estimation model, one or more LoS estimations based on the patient attribute data of each of the one or more patient encounter records; and   generate, via a metric analyzer, one or more evaluation metrics based on the one or more LoS estimations and the patient LoS data of each of the one or more patient encounter records.   
     
     
         2 . The system of  claim 1 , further comprising a user interface configured to display at least a portion of the one or more evaluation metrics. 
     
     
         3 . The system of  claim 1 , wherein the controller is further configured to extract, via a feature extractor, at least a portion of the one or more patient encounter records from contemporary electronic medical records (EMR). 
     
     
         4 . The system of  claim 1 , wherein the patient attribute data comprises vital sign data, patient demographic data, laboratory data, medical condition data, infection type data, medication administration data, and/or discharge type. 
     
     
         5 . The system of  claim 1 , wherein the controller is further configured to train the LoS estimation model with a plurality of historical encounter records, wherein each of the plurality of historical encounter records comprises historical attribute data and historical recovery data. 
     
     
         6 . The system of  claim 5 , wherein the historical recovery data comprises right-censored recovery data corresponding to patient discharge prior to recovery. 
     
     
         7 . The system of  claim 5 , wherein the historical attribute data comprises historical vital sign data, historical demographic data, historical laboratory data, historical medical condition data, historical infection type data, historical medication administration data, and/or historical discharge type. 
     
     
         8 . The system of  claim 5 , wherein the controller is further configured to extract, via a feature extractor, at least a portion of the plurality of historical encounter records from historical electronic medical records (EMR). 
     
     
         9 . The system of  claim 5 , wherein the controller is further configured to generate, via the plurality of historical encounter records, a concordance index value of the LoS estimation model. 
     
     
         10 . The system of  claim 9 , wherein the controller is further configured to divide the plurality of historical encounter records into five folds. 
     
     
         11 . The system of  claim 10 , wherein the plurality of historical encounter records is divided in the five folds based on historical gender and historical discharge type. 
     
     
         12 . The system of  claim 9 , wherein the controller is further configured to adjust one or more regularization parameters of the LoS estimation model based on the concordance index value. 
     
     
         13 . A method for infection treatment evaluation, comprising:
 receiving, via a controller having a processor and a memory, one or more patient encounter records, wherein each one of the one or more patient encounter records comprises patient attribute data and patient length of stay (LoS) data;   generating, via an LoS estimation model of the controller, one or more LoS estimations based on the patient attribute data of each of the one or more patient encounter records; and   generating, via a metric analyzer of the controller, one or more evaluation metrics based on the one or more LOS estimations and the patient LoS data of each of the one or more patient encounter records.   
     
     
         14 . The method of  claim 13 , further comprising displaying, via a user interface, at least a portion of the one or more evaluation metrics. 
     
     
         15 . The method of  claim 13 , further comprising training the LoS estimation model with a plurality of historical encounter records, wherein each of the plurality of historical encounter records comprises historical attribute data and historical recovery data.